def test_compute_features_import_2(self):
"""
Unit test compute_features_import 2
Checking classification case
"""
xpl = SmartExplainer()
contrib1 = pd.DataFrame(
[[1, 2, 3, 4],
[5, 6, 7, 8],
[9, 10, 11, 12]],
columns=['contribution_0', 'contribution_1', 'contribution_2', 'contribution_3'],
index=[0, 1, 2]
)
contrib2 = pd.DataFrame(
[[13, 14, 15, 16],
[17, 18, 19, 20],
[21, 22, 23, 24]],
columns=['contribution_0', 'contribution_1', 'contribution_2', 'contribution_3'],
index=[0, 1, 2]
)
contributions = [contrib1, contrib2]
xpl.features_imp = None
xpl.contributions = contributions
xpl.state = xpl.choose_state(contributions)
xpl._case = "classification"
xpl.compute_features_import()
expect1 = contrib1.abs().sum().sort_values(ascending=True)
expect1 = expect1 / expect1.sum()
expect2 = contrib2.abs().sum().sort_values(ascending=True)
expect2 = expect2 / expect2.sum()
assert expect1.equals(xpl.features_imp[0])
assert expect2.equals(xpl.features_imp[1])
def test_check_contributions_1(self):
"""
Unit test check contributions 1
"""
xpl = SmartExplainer()
xpl.contributions, xpl.x_pred = Mock(), Mock()
xpl.state = Mock()
xpl.check_contributions()
xpl.state.check_contributions.assert_called_with(xpl.contributions, xpl.x_pred)
def test_to_pandas_1(self):
"""
Unit test to pandas 1
"""
xpl = SmartExplainer()
xpl.state = SmartState()
data = {}
data['contrib_sorted'] = pd.DataFrame(
[[0.32230754, 0.1550689, 0.10183475, 0.05471339],
[-0.58547512, -0.37050409, -0.07249285, 0.00171975],
[-0.48666675, 0.25507156, -0.16968889, 0.0757443]],
columns=[
'contribution_0', 'contribution_1', 'contribution_2',
'contribution_3'
],
index=[0, 1, 2])
data['var_dict'] = pd.DataFrame(
[[1, 0, 2, 3], [1, 0, 3, 2], [1, 0, 2, 3]],
columns=['feature_0', 'feature_1', 'feature_2', 'feature_3'],
index=[0, 1, 2])
data['x_sorted'] = pd.DataFrame(
[[1., 3., 22., 1.], [2., 1., 2., 38.], [2., 3., 26., 1.]],
columns=['feature_0', 'feature_1', 'feature_2', 'feature_3'],
index=[0, 1, 2])
xpl.data = data
xpl.columns_dict = {0: 'Pclass', 1: 'Sex', 2: 'Age', 3: 'Embarked'}
xpl.features_dict = {
'Pclass': 'Pclass',
'Sex': 'Sex',
'Age': 'Age',
'Embarked': 'Embarked'
}
xpl.x = pd.DataFrame(
[[3., 1., 22., 1.], [1., 2., 38., 2.], [3., 2., 26., 1.]],
columns=['Pclass', 'Sex', 'Age', 'Embarked'],
index=[0, 1, 2])
xpl.x_pred = xpl.x
xpl.contributions = data['contrib_sorted']
xpl.y_pred = pd.DataFrame([1, 2, 3], columns=['pred'], index=[0, 1, 2])
model = lambda: None
model.predict = types.MethodType(self.predict, model)
xpl.model = model
xpl._case, xpl._classes = xpl.check_model()
xpl.state = xpl.choose_state(xpl.contributions)
output = xpl.to_pandas(max_contrib=2)
expected = pd.DataFrame(
[[1, 'Sex', 1.0, 0.32230754, 'Pclass', 3.0, 0.1550689],
[2, 'Sex', 2.0, -0.58547512, 'Pclass', 1.0, -0.37050409],
[3, 'Sex', 2.0, -0.48666675, 'Pclass', 3.0, 0.25507156]],
columns=[
'pred', 'feature_1', 'value_1', 'contribution_1', 'feature_2',
'value_2', 'contribution_2'
],
index=[0, 1, 2],
dtype=object)
expected['pred'] = expected['pred'].astype(int)
assert not pd.testing.assert_frame_equal(expected, output)
def test_check_contributions_2(self):
"""
Unit test check contributions 2
"""
xpl = SmartExplainer()
xpl.contributions, xpl.x_pred = Mock(), Mock()
mock_state = Mock()
mock_state.check_contributions.return_value = False
xpl.state = mock_state
with self.assertRaises(ValueError):
xpl.check_contributions()
def test_check_model_2(self):
"""
Unit test check model 2
"""
xpl = SmartExplainer()
df1 = pd.DataFrame([1, 2])
df2 = pd.DataFrame([3, 4])
xpl.contributions = [df1, df2]
xpl.state = xpl.choose_state(xpl.contributions)
model = lambda: None
model._classes = np.array([1, 2])
model.predict = types.MethodType(self.predict, model)
model.predict_proba = types.MethodType(self.predict_proba, model)
xpl.model = model
xpl._case, xpl._classes = xpl.check_model()
assert xpl._case == 'classification'
self.assertListEqual(xpl._classes, [1, 2])
def test_compute_features_import_1(self):
"""
Unit test compute_features_import 1
Checking regression case
"""
xpl = SmartExplainer()
contributions = pd.DataFrame(
[[1, 2, 3, 4],
[5, 6, 7, 8],
[9, 10, 11, 12]],
columns=['contribution_0', 'contribution_1', 'contribution_2', 'contribution_3'],
index=[0, 1, 2]
)
xpl.features_imp = None
xpl.contributions = contributions
xpl.state = xpl.choose_state(contributions)
xpl._case = 'regression'
xpl.compute_features_import()
expected = contributions.abs().sum().sort_values(ascending=True)
expected = expected / expected.sum()
assert expected.equals(xpl.features_imp)
